Pulse-Coupled Neural Networks

Johnson, John L.; Ranganath, Heggere S.; Kuntimad, Govindaraj; Caulfield, H. John

doi:10.1016/b978-012526420-4/50002-1

Cited by 35 publications

(8 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Pioneering work in the implementation of these algorithms was done by Johnson and his colleagues [11][12][13][14][15][16]. It has been proven that PCNN is very suitable for image processing [15,16] such as image segmentation, image enhancement, pattern recognition, etc.…”

Section: Introductionmentioning

confidence: 99%

Medical image fusion using m-PCNN

2008

View full text Add to dashboard Cite

Section: Introductionmentioning

confidence: 99%

Medical image fusion using m-PCNN

2008

View full text Add to dashboard Cite

“…Due to this discovery they developed a neural network, called Eckhorn"s model, to simulate this behavior.In the early 1990s, Rybak et al also found the similar neural behavior based on the study of the visual cortex of the guinea pig and developed a neural network, called Rybak"s model [9,10]. Because Eckhorn"s model and Rybak" model provided a simple, effective way for studying synchronous pulse dynamics in networks,they was recognized as being very potential in image processing [11][12][13]. The functioning of the visual cortex has to be studied in order to develop algorithms.…”

Section: Related Workmentioning

confidence: 99%

Preservation of Historical Documents using ICM and Filters

Parvin¹,

Nisha²,

Sathik³

2017

International Journal of Advanced Research in Computer and Comm

View full text Add to dashboard Cite

Digital image enhancement technique is used for improving the visual qualities of the images. In this paper, contaminated Brahmi script is taken as an input and it is enhanced. There are numerous problems in preserving historical documents from degradation due to some bad storage conditions and poor contrast due to humidity. In this work, it is proposed to investigate the efficiency of logarithmic technique to enhance along with the performance of utilizing the Intersecting Cortical Model (ICM) network which is a simplified model of Pulse-Coupled Neural Network (PCNN) model and filters.

show abstract

“…If time of arrival is used as the information carrier, it demonstrates that mechanism exist in the cellular architectures to perform histogram analysis and adaptive histogram analysis of images [26]. Johnson [27] states that the time signals are unique, object-specific and roughly invariant time signature for their corresponding input spatial image or distribution.…”

Section: B Image Processing Applicationsmentioning

confidence: 99%

Analog implementation of pulse-coupled neural networks

Ota¹,

Wilamowski²

1999

IEEE Trans. Neural Netw.

View full text Add to dashboard Cite

Abstract-This paper presents a compact architecture for analog CMOS hardware implementation of voltage-mode pulsecoupled neural networks (PCNN's). The hardware implementation methods shows inherent fault tolerance specialties and high speed, which is usually more than an order of magnitude over the software counterpart. A computational style described in this article mimics a biological neural network using pulse-stream signaling and analog summation and multiplication. Pulse-stream encoding technique uses pulse streams to carry information and control analog circuitry, while storing further analog information on the time axis. The main feature of the proposed neuron circuit is that the structure is compact, yet exhibiting all the basic properties of natural biological neurons. Functional and structural forms of neural and synaptic functions are presented along with simulation results. Finally, the proposed design is applied to image processing to demonstrate successful restoration of images and their features.

show abstract

Pulse-Coupled Neural Networks

Cited by 35 publications

References 15 publications

Medical image fusion using m-PCNN

Medical image fusion using m-PCNN

Preservation of Historical Documents using ICM and Filters

Analog implementation of pulse-coupled neural networks

Contact Info

Product

Resources

About